Start typing to search.
Ranks providers by their recent typical output speed in tokens per second. Providers without enough recent data remain visible after ranked rows.
Weights & Biases currently ranks first at 191.0 tok/s via wandb/int4.
| Rank | Provider / route | Output speed | Speed measurements | Endpoint details |
|---|---|---|---|---|
| #1 | Provider / route Weights & Biases wandb/int4 | Output speed191.0 tok/s | Speed measurements
| Endpoint details
|
| #2 | Provider / route Together together | Output speed152.0 tok/s | Speed measurements
| Endpoint details
|
| #3 | Provider / route ModelRun modelrun/fp4 | Output speed147.0 tok/s | Speed measurements
| Endpoint details
|
| #4 | Provider / route Inceptron inceptron/int4 | Output speed91.0 tok/s | Speed measurements
| Endpoint details
|
| #5 | Provider / route Venice venice/int4 | Output speed85.0 tok/s | Speed measurements
| Endpoint details
|
| #6 | Provider / route Fireworks fireworks | Output speed79.5 tok/s | Speed measurements
| Endpoint details
|
| #7 | Provider / route DeepInfra deepinfra/fp4 | Output speed77.5 tok/s | Speed measurements
| Endpoint details
|
| #8 | Provider / route Parasail parasail/int4 | Output speed75.5 tok/s | Speed measurements
| Endpoint details
|
| #9 | Provider / route Moonshot AI moonshotai/highspeed | Output speed63.0 tok/s | Speed measurements
| Endpoint details
|
| #10 | Provider / route Cloudflare cloudflare | Output speed53.0 tok/s | Speed measurements
| Endpoint details
|
| #11 | Provider / route Ambient ambient/int4 | Output speed45.0 tok/s | Speed measurements
| Endpoint details
|
| #12 | Provider / route SiliconFlow siliconflow/fp8 | Output speed40.5 tok/s | Speed measurements
| Endpoint details
|
| #13 | Provider / route Moonshot AI moonshotai/int4 | Output speed36.0 tok/s | Speed measurements
| Endpoint details
|
| #14 | Provider / route AtlasCloud atlas-cloud/int4 | Output speed20.0 tok/s | Speed measurements
| Endpoint details
|
| #15 | Provider / route NovitaAI novita/int4 | Output speed8.0 tok/s | Speed measurements
| Endpoint details
|
Endpoint data fetched .
Kimi K2.7 Code endpoint guide
15 of 15 Kimi K2.7 Code endpoints currently have the published data required for this ranking. Weights & Biases leads at 191.0 tok/s via wandb/int4. The table keeps unranked routes visible so missing measurements do not look like missing provider availability.
The output-speed ranking compares recent median generated tokens per second. It favors routes that complete long generations quickly, while first-token latency remains a separate measure of how responsive the endpoint feels at the beginning.
Together currently ranks second at 152.0 tok/s. Compare that gap with input and output price, response-start time, output speed, 30-minute uptime, context length, and the exact route before deciding whether first place is meaningful for your workload.
Kimi K2.7 Code has 15 published provider options, and performance data is matched to each exact OpenRouter routing tag. Different quantization, context, regional deployment, or provider configuration can change price and behavior even when the underlying model name is identical.
